openai-whisper-api

To transcribe audio recordings into text, this Skill posts multipart form data to the OpenAI Whisper API endpoint /v1/audio/transcriptions using a curl-based workflow, requiring an OPENAI_API_KEY.

Yes, you can transcribe podcasts, interviews, and meetings into searchable text transcripts by running the provided curl script, which sends your audio files directly to the Whisper API.

Yes, an OPENAI_API_KEY is required to authenticate curl requests for speech-to-text transcription. You can also optionally configure an OPENAI_BASE_URL to route the API calls.

The best way to convert audio files to searchable transcripts with Whisper is using a simple curl-based workflow that posts audio data to the /v1/audio/transcriptions endpoint with model and language options.

Yes, the curl-based transcription workflow supports language options when sending audio data to the OpenAI Whisper API, allowing you to process recordings accurately according to their spoken language.

Using curl to post multipart form data for audio transcription provides a lightweight, dependency-minimal method to send audio files directly to the Whisper API endpoint, bypassing complex library setups.